© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47228
    Prev
    Next
    INDEX
    Explanations

    Xilinx

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    نا
    0.87
    ني
    0.82
    ي
    0.80
    نية
    0.79
    ת
    0.77
    ர
    0.75
    는
    0.75
    ние
    0.74
    是真的
    0.73
    نة
    0.73
    POSITIVE LOGITS
    pets
    0.87
    c
    0.79
    and
    0.79
    ai
    0.76
    courses
    0.71
    h
    0.70
     a
    0.68
    paths
    0.68
    charts
    0.66
    cards
    0.65
    Activations Density 0.010%

    No Known Activations